Márk Antal Csizmadia's Projects
Deep convolutional generative adversarial networks (DCGANs) for generating fake faces with Tensorflow and Keras.
Replication of the research paper titled Auto-Encoding Variational Bayes.
Discovery of Frequent Itemsets and Association Rules with the Apriori algorithm. Made with Python and PySpark.
Eigenfaces exercise. Started from here with ML.
Expectation Maximization (EM) algorithm for estimating maximum likelihood (ML) parameters of partially observed data on a three-node Bayesian Network Probabilistic Graphical Model.
Finding Similar Items: Textually Similar Documents
A collection of useful .gitignore templates
Analyzing product co-purchasing networks as graphs.
Basic applications with Hadoop MapReduce and HBase.
Hidden Markov Models (HMMs) for estimating the sequence of hidden states (decoding) via the Viterbi algorithm, and estimating model parameters (learning) via the Baum- Welch algorithm.
Implementing Hopfield Networks from scratch, testing their content addressable memory, attractor, and energy landscape, investigating their resistance to noise, experimenting with their memory capacity, and putting strain on them with sparse patterns.
Implementation of the HyperBall algorithm with HyperLogLogCounters from the paper titled "In-Core Computation of Geometric Centralities with HyperBall: A Hundred Billion Nodes and Beyond".
GitHub profile readme
GitHub IO page.
Naive implementation of Convolution Neural Networks (CNNs). Example architecture LeNet5 on MNIST hand-written digits.
A neural network library built from scratch, without dedicated deep learning packages. Training and testing deep neural networks and utilizing deep learning best practices for multi-class classification with fully connected neural networks, text generation with recurrent neural networks, and regression with fully connected networks.
Dimensionality reduction and data embedding via PCA, MDS, and Isomap.
My personal website built with Django. An absolute overkill ... but good practice. Will set up a normal portfolio website with Github pages.
Restricted Boltzmann Machines (RBMs) and Deep Belief Networks (DBNs) from scratch for representation learning on the MNIST dataset.
Re-implementation of the paper titled "Noise against noise: stochastic label noise helps combat inherent label noise" from ICLR 2021.
Concise, consistent, and legible badges in SVG and raster format
Single Layer Perceptrons (SLPs) and Multi-Layer Perceptrons (MLPs) from scratch, only with numpy, for classification and regression. MLPs with Keras for time-series prediction.
Kohonen Self-Organizing Maps (SOMs) for dimensionality reduction, data embedding, and solving a variant of the travelling salesman problem.
Basics with Spark via PySpark.
Re-implementation of the paper titled "On Spectral Clustering: Analysis and an algorithm" by AY Ng et al.
Support Vector Machines (SVMs) from scratch, without dedicated packages, for the classification of linear and non-linear data.
Factorized variational approximation using a univariate Gaussian distribution over a single variable x.
Coordinate ascent mean-field variational inference (CAVI) using the evidence lower bound (ELBO) to iteratively perform the optimal variational factor distribution parameter updates for clustering.